all AI news
Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later
March 27, 2024, 4:46 a.m. | Binxu Wang, John J. Vastola
cs.CV updates on arXiv.org arxiv.org
Abstract: How do diffusion generative models convert pure noise into meaningful images? In a variety of pretrained diffusion models (including conditional latent space models like Stable Diffusion), we observe that the reverse diffusion process that underlies image generation has the following properties: (i) individual trajectories tend to be low-dimensional and resemble 2D `rotations'; (ii) high-variance scene features like layout tend to emerge earlier, while low-variance details tend to emerge later; and (iii) early perturbations tend to …
abstract arxiv cs.ai cs.cv cs.gr cs.ne diffusion diffusion models generate generative generative models image image generation images noise observe process space stable diffusion theory type
More from arxiv.org / cs.CV updates on arXiv.org
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
2 days, 3 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Research Scientist
@ Meta | Menlo Park, CA
Principal Data Scientist
@ Mastercard | O'Fallon, Missouri (Main Campus)